my $facets_counter = {};
my $facets_info = {};
my $facets = getFacets();
- my $facets_maxrecs = C4::Context->preference('maxRecordsForFacets')||20;
my @facets_loop; # stores the ref to array of hashes for template facets loop
# Fill the facets while we're looping, but only for the
# biblioserver and not for a scan
if ( !$scan && $servers[ $i - 1 ] =~ /biblioserver/ ) {
-
- my $jmax = $size > $facets_maxrecs
- ? $facets_maxrecs
- : $size;
-
- for ( my $j = 0 ; $j < $jmax ; $j++ ) {
-
- my $marc_record = new_record_from_zebra (
- 'biblioserver',
- $results[ $i - 1 ]->record($j)->raw()
- );
-
- if ( ! defined $marc_record ) {
- warn "ERROR DECODING RECORD - $@: " .
- $results[ $i - 1 ]->record($j)->raw();
- next;
- }
-
- _get_facets_data_from_record( $marc_record, $facets, $facets_counter, $facets_info );
- }
+ $facets_counter = GetFacets( $results[ $i - 1 ] );
+ $facets_info = _get_facets_info( $facets );
}
- # warn "connection ", $i-1, ": $size hits";
- # warn $results[$i-1]->record(0)->render() if $size > 0;
-
# BUILD FACETS
if ( $servers[ $i - 1 ] =~ /biblioserver/ ) {
for my $link_value (
return ( undef, $results_hashref, \@facets_loop );
}
+sub GetFacets {
+
+ my $rs = shift;
+ my $facets;
+
+ my $indexing_mode = C4::Context->config('zebra_bib_index_mode') // 'dom';
+ my $use_zebra_facets = C4::Context->config('use_zebra_facets') // 0;
+
+ if ( $indexing_mode eq 'dom' &&
+ $use_zebra_facets ) {
+ $facets = _get_facets_from_zebra( $rs );
+ } else {
+ $facets = _get_facets_from_records( $rs );
+ }
+
+ return $facets;
+}
+
+sub _get_facets_from_records {
+
+ my $rs = shift;
+
+ my $facets_maxrecs = C4::Context->preference('maxRecordsForFacets') // 20;
+ my $facets_config = getFacets();
+ my $facets = {};
+ my $size = $rs->size();
+ my $jmax = $size > $facets_maxrecs
+ ? $facets_maxrecs
+ : $size;
+
+ for ( my $j = 0 ; $j < $jmax ; $j++ ) {
+
+ my $marc_record = new_record_from_zebra (
+ 'biblioserver',
+ $rs->record( $j )->raw()
+ );
+
+ if ( ! defined $marc_record ) {
+ warn "ERROR DECODING RECORD - $@: " .
+ $rs->record( $j )->raw();
+ next;
+ }
+
+ _get_facets_data_from_record( $marc_record, $facets_config, $facets );
+ }
+
+ return $facets;
+}
+
=head2 _get_facets_data_from_record
C4::Search::_get_facets_data_from_record( $marc_record, $facets, $facets_counter );
sub _get_facets_data_from_record {
- my ( $marc_record, $facets, $facets_counter, $facets_info ) = @_;
+ my ( $marc_record, $facets, $facets_counter ) = @_;
for my $facet (@$facets) {
foreach my $tag ( @{ $facet->{ tags } } ) {
- # avoid first line
+ # tag number is the first three digits
my $tag_num = substr( $tag, 0, 3 );
+ # subfields are the remainder
my $subfield_letters = substr( $tag, 3 );
- # Removed when as_string fixed
- my @subfields = $subfield_letters =~ /./sg;
my @fields = $marc_record->field( $tag_num );
foreach my $field (@fields) {
+ # If $field->indicator(1) eq 'z', it means it is a 'see from'
+ # field introduced because of IncludeSeeFromInSearches, so skip it
+ next if $field->indicator(1) eq 'z';
+
my $data = $field->as_string( $subfield_letters, $facet->{ sep } );
unless ( grep { /^\Q$data\E$/ } @used_datas ) {
}
}
}
- # update $facets_info so we know what facet categories need to be rendered
+ }
+}
+
+=head2 _get_facets_from_zebra
+
+ my $facets = _get_facets_from_zebra( $result_set )
+
+Retrieves facets for a specified result set. It loops through the facets defined
+in C4::Koha::getFacets and returns a hash with the following structure:
+
+ { facet_idx => {
+ facet_value => count
+ },
+ ...
+ }
+
+=cut
+
+sub _get_facets_from_zebra {
+
+ my $rs = shift;
+
+ # save current elementSetName
+ my $elementSetName = $rs->option( 'elementSetName' );
+
+ my $facets_loop = getFacets();
+ my $facets_data = {};
+ # loop through defined facets and fill the facets hashref
+ foreach my $facet ( @$facets_loop ) {
+
+ my $idx = $facet->{ idx };
+ my $sep = $facet->{ sep };
+ my $facet_values = _get_facet_from_result_set( $idx, $rs, $sep );
+ if ( $facet_values ) {
+ # we've actually got a result
+ $facets_data->{ $idx } = $facet_values;
+ }
+ }
+ # set elementSetName to its previous value to avoid side effects
+ $rs->option( elementSetName => $elementSetName );
+
+ return $facets_data;
+}
+
+=head2 _get_facet_from_result_set
+
+ my $facet_values =
+ C4::Search::_get_facet_from_result_set( $facet_idx, $result_set, $sep )
+
+Internal function that extracts facet information for a specific index ($facet_idx) and
+returns a hash containing facet values and count:
+
+ {
+ $facet_value => $count ,
+ ...
+ }
+
+Warning: this function has the side effect of changing the elementSetName for the result
+set. It is a helper function for the main loop, which takes care of backing it up for
+restoring.
+
+=cut
+
+sub _get_facet_from_result_set {
+
+ my $facet_idx = shift;
+ my $rs = shift;
+ my $sep = shift;
+
+ my $internal_sep = '<*>';
+ my $facetMaxCount = C4::Context->preference('FacetMaxCount') // 20;
+
+ return if ( ! defined $facet_idx || ! defined $rs );
+ # zebra's facet element, untokenized index
+ my $facet_element = 'zebra::facet::' . $facet_idx . ':0:' . $facetMaxCount;
+ # configure zebra results for retrieving the desired facet
+ $rs->option( elementSetName => $facet_element );
+ # get the facet record from result set
+ my $facet = $rs->record( 0 )->raw;
+ # if the facet has no restuls...
+ return if !defined $facet;
+ # TODO: benchmark DOM vs. SAX performance
+ my $facet_dom = XML::LibXML->load_xml(
+ string => ($facet)
+ );
+ my @terms = $facet_dom->getElementsByTagName('term');
+ return if ! @terms;
+
+ my $facets = {};
+ foreach my $term ( @terms ) {
+ my $facet_value = $term->textContent;
+ $facet_value =~ s/\Q$internal_sep\E/$sep/ if defined $sep;
+ $facets->{ $facet_value } = $term->getAttribute( 'occur' );
+ }
+
+ return $facets;
+}
+
+=head2 _get_facets_info
+
+ my $facets_info = C4::Search::_get_facets_info( $facets )
+
+Internal function that extracts facets information and properly builds
+the data structure needed to render facet labels.
+
+=cut
+
+sub _get_facets_info {
+
+ my $facets = shift;
+
+ my $facets_info = {};
+
+ for my $facet ( @$facets ) {
$facets_info->{ $facet->{ idx } }->{ label_value } = $facet->{ label };
$facets_info->{ $facet->{ idx } }->{ expanded } = $facet->{ expanded };
}
+
+ return $facets_info;
}
sub pazGetRecords {
my $index = $indexes[$i];
# Add index-specific attributes
+
+ #Afaik, this 'yr' condition will only ever be met in the staff client advanced search
+ #for "Publication date", since typing 'yr:YYYY' into the search box produces a CCL query,
+ #which is processed higher up in this sub. Other than that, year searches are typically
+ #handled as limits which are not processed her either.
+
# Date of Publication
- if ( $index eq 'yr' ) {
- $index .= ",st-numeric";
- $indexes_set++;
+ if ( $index =~ /yr/ ) {
+ #weight_fields/relevance search causes errors with date ranges
+ #In the case of YYYY-, it will only return records with a 'yr' of YYYY (not the range)
+ #In the case of YYYY-YYYY, it will return no results
$stemming = $auto_truncation = $weight_fields = $fuzzy_enabled = $remove_stopwords = 0;
}
# Date of Acquisition
- elsif ( $index eq 'acqdate' ) {
- $index .= ",st-date-normalized";
- $indexes_set++;
+ elsif ( $index =~ /acqdate/ ) {
+ #stemming and auto_truncation would have zero impact since it already is YYYY-MM-DD format
+ #Weight_fields probably SHOULD be turned OFF, otherwise you'll get records floating to the
+ #top of the results just because they have lots of item records matching that date.
+ #Fuzzy actually only applies during _build_weighted_query, and is reset there anyway, so
+ #irrelevant here
+ #remove_stopwords doesn't function anymore so is irrelevant
$stemming = $auto_truncation = $weight_fields = $fuzzy_enabled = $remove_stopwords = 0;
}
# ISBN,ISSN,Standard Number, don't need special treatment
# This is flawed , means we can't search anything with : in it
# if user wants to do ccl or cql, start the query with that
# $query =~ s/:/=/g;
+ #NOTE: We use several several different regexps here as you can't have variable length lookback assertions
$query =~ s/(?<=(ti|au|pb|su|an|kw|mc|nb|ns)):/=/g;
$query =~ s/(?<=(wrdl)):/=/g;
$query =~ s/(?<=(trn|phr)):/=/g;
+ $query =~ s/(?<=(st-numeric)):/=/g;
+ $query =~ s/(?<=(st-year)):/=/g;
+ $query =~ s/(?<=(st-date-normalized)):/=/g;
$limit =~ s/:/=/g;
for ( $query, $query_desc, $limit, $limit_desc ) {
s/ +/ /g; # remove extra spaces
my $raw_data = shift;
# Set the default indexing modes
my $index_mode = ( $server eq 'biblioserver' )
- ? C4::Context->config('zebra_bib_index_mode') // 'grs1'
+ ? C4::Context->config('zebra_bib_index_mode') // 'dom'
: C4::Context->config('zebra_auth_index_mode') // 'dom';
my $marc_record = eval {